Langgraph Docs
Pull authoritative LangGraph Python docs into the agent so you can implement stateful graphs, multi-agent workflows, and human-in-the-loop patterns without guessing APIs.
Overview
langgraph-docs is an agent skill for the Build phase that fetches official LangGraph Python documentation and applies it to stateful agents, multi-agent workflows, and human-in-the-loop implementation questions.
Install
npx skills add https://github.com/langchain-ai/deepagents --skill langgraph-docsWhat is this skill?
- Three-step workflow: fetch llms.txt index, pick 2–4 URLs, fetch_url and apply answers
- Prioritizes how-to guides, concept pages, tutorials, and API reference from the official index
- Covers stateful agents, multi-agent workflows, human-in-the-loop, and LangGraph API questions
- Single retry on fetch_url failure with fallback to langchain-ai.github.io/langgraph
- 3-step workflow: index fetch, 2–4 URL selection, apply documentation
Adoption & trust: 3.4k installs on skills.sh; 24.2k GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You are building LangGraph agents but need current official docs and the right pages instead of hallucinated APIs or outdated patterns.
Who is it for?
Solo builders implementing LangGraph state graphs, checkpoints, and multi-agent flows who want live doc retrieval in Claude Code, Cursor, or Codex.
Skip if: Teams that forbid network fetches, projects not using LangGraph/LangChain, or users who only need copy-paste templates without reading official reference.
When should I use this skill?
User asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
What do I get? / Deliverables
The agent returns answers grounded in freshly fetched LangGraph documentation from the curated index and selected doc URLs.
- Answers grounded in fetched LangGraph documentation pages
- List of official doc URLs used for the response
Recommended Skills
Journey fit
Canonical shelf is Build because the skill exists to implement and orchestrate LangGraph agents during product construction. Agent-tooling is the best fit: the workflow centers on LangGraph graphs, state machines, and orchestration—not generic frontend or PM work.
How it compares
Use as a doc-retrieval companion skill, not a replacement for LangGraph project scaffolds or MCP servers that expose runtime tools.
Common Questions / FAQ
Who is langgraph-docs for?
Indie and solo developers building Python LangGraph agents who want the coding agent to cite and follow current LangChain documentation.
When should I use langgraph-docs?
During Build agent-tooling when you ask about LangGraph APIs, graph design, orchestration, or human-in-the-loop patterns and need the agent to fetch docs.langchain.com content first.
Is langgraph-docs safe to install?
It mainly reads public documentation URLs; review the Security Audits panel on this Prism page and restrict network use in sensitive environments.
SKILL.md
READMESKILL.md - Langgraph Docs
# langgraph-docs ## Workflow ### 1. Fetch the Documentation Index Use `fetch_url` to read: https://docs.langchain.com/llms.txt This returns a structured list of all available documentation with descriptions. ### 2. Select Relevant Documentation Identify 2-4 most relevant URLs from the index. Prioritize: - **Implementation questions** — specific how-to guides - **Conceptual questions** — core concept pages - **End-to-end examples** — tutorials - **API details** — reference docs ### 3. Fetch and Apply Use `fetch_url` on the selected URLs, then complete the user's request using the documentation content. If `fetch_url` fails or returns empty content, retry once. If it fails again, inform the user and suggest checking https://langchain-ai.github.io/langgraph/ directly.